Numerical‐discrete‐scheme‐incorporated recurrent neural network for tasks in natural language processing

作     者：Mei Liu Wendi Luo Zangtai Cai Xiujuan Du Jiliang Zhang Shuai Li 

作者机构：School of Information Science and EngineeringLanzhou UniversityLanzhouChina The State Key Laboratory of Tibetan Intelligent Information Processing and ApplicationQinghai Normal UniversityXiningChina Department of Electronic and Electrical EngineeringThe University of SheffieldSheffieldUK 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2023年第8卷第4期

页      面：1415-1424页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

基　　金：supported in part by the National Natural Science Foundation of China under Grant 62176109 in part by the Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province under Grant 2021‐Z‐003 in part by the Natural Science Foundation of Gansu Province under Grant 21JR7RA531 and Grant 22JR5RA487 in part by the Fundamental Research Funds for the Central Universities under Grant lzujbky‐2022‐23 in part by the CAAI‐Huawei MindSpore Open Fund under Grant CAAIXSJLJJ‐2022‐020A in part by the Supercomputing Center of Lanzhou University,in part by Sichuan Science and Technology Program No.2022nsfsc0916 

主　　题：deep learning natural language processing neural network text analysis 

摘      要：A variety of neural networks have been presented to deal with issues in deep learning in the last *** the prominent success achieved by the neural network,it still lacks theoretical guidance to design an efficient neural network model,and verifying the performance of a model needs excessive *** research studies have demonstrated that many existing models can be regarded as different numerical discretizations of differential *** connection sheds light on designing an effective recurrent neural network(RNN)by resorting to numerical *** RNN is regarded as a discretisation of the forward Euler *** the limited solution accuracy of the forward Euler methods,a Taylor‐type discrete scheme is presented with lower truncation error and a Taylor‐type RNN(T‐RNN)is designed with its *** experiments are conducted to evaluate its performance on statistical language models and emotion analysis *** noticeable gains obtained by T‐RNN present its superiority and the feasibility of designing the neural network model using numerical methods.